submission_id: riverise-dpo-second_v1
developer_uid: Riverise
alignment_samples: 11112
alignment_score: -0.09978136829399388
best_of: 16
celo_rating: 1242.59
display_name: riverise-dpo-second_v1
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 64}
is_internal_developer: False
language_model: Riverise/dpo-second
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: Riverise/dpo-second
model_name: riverise-dpo-second_v1
model_num_parameters: 8030261248.0
model_repo: Riverise/dpo-second
model_size: 8B
num_battles: 11112
num_wins: 5716
propriety_score: 0.745119305856833
propriety_total_count: 922.0
ranking_group: single
status: inactive
submission_type: basic
timestamp: 2024-09-01T07:45:17+00:00
us_pacific_date: 2024-09-01
win_ratio: 0.5143988480921526
Download Preference Data
Resubmit model
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name riverise-dpo-second-v1-mkmlizer
Waiting for job on riverise-dpo-second-v1-mkmlizer to finish
Stopping job with name riverise-dpo-second-v1-mkmlizer
%s, retrying in %s seconds...
Starting job with name riverise-dpo-second-v1-mkmlizer
Waiting for job on riverise-dpo-second-v1-mkmlizer to finish
riverise-dpo-second-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-dpo-second-v1-mkmlizer: ║     _____            __           __                                ║
riverise-dpo-second-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
riverise-dpo-second-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
riverise-dpo-second-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
riverise-dpo-second-v1-mkmlizer: ║       /___/                                                         ║
riverise-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-dpo-second-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
riverise-dpo-second-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
riverise-dpo-second-v1-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-dpo-second-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-dpo-second-v1-mkmlizer: ║  belonging to:                                                      ║
riverise-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-dpo-second-v1-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-dpo-second-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-dpo-second-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
riverise-dpo-second-v1-mkmlizer: ║                                                                     ║
riverise-dpo-second-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
riverise-dpo-second-v1-mkmlizer: Downloaded to shared memory in 62.465s
riverise-dpo-second-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmph9wp6hbr, device:0
riverise-dpo-second-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-dpo-second-v1-mkmlizer: quantized model in 28.936s
riverise-dpo-second-v1-mkmlizer: Processed model Riverise/dpo-second in 91.402s
riverise-dpo-second-v1-mkmlizer: creating bucket guanaco-mkml-models
riverise-dpo-second-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-dpo-second-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-dpo-second-v1
riverise-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-dpo-second-v1/config.json
riverise-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-dpo-second-v1/special_tokens_map.json
riverise-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-dpo-second-v1/tokenizer_config.json
riverise-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-dpo-second-v1/tokenizer.json
riverise-dpo-second-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-dpo-second-v1/flywheel_model.0.safetensors
riverise-dpo-second-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:10, 26.33it/s]
Loading 0:   4%|▍         | 12/291 [00:00<00:07, 35.35it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:08, 33.61it/s]
Loading 0:   7%|▋         | 21/291 [00:00<00:07, 36.74it/s]
Loading 0:   9%|▊         | 25/291 [00:00<00:07, 34.61it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:06, 40.65it/s]
Loading 0:  12%|█▏        | 36/291 [00:01<00:10, 24.71it/s]
Loading 0:  14%|█▍        | 41/291 [00:01<00:09, 26.11it/s]
Loading 0:  16%|█▋        | 48/291 [00:01<00:07, 31.97it/s]
Loading 0:  18%|█▊        | 52/291 [00:01<00:07, 30.90it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:06, 33.70it/s]
Loading 0:  21%|██        | 61/291 [00:01<00:07, 32.45it/s]
Loading 0:  23%|██▎       | 66/291 [00:02<00:06, 34.14it/s]
Loading 0:  24%|██▍       | 70/291 [00:02<00:06, 33.31it/s]
Loading 0:  25%|██▌       | 74/291 [00:02<00:06, 33.48it/s]
Loading 0:  27%|██▋       | 78/291 [00:02<00:06, 33.43it/s]
Loading 0:  28%|██▊       | 82/291 [00:02<00:08, 24.09it/s]
Loading 0:  29%|██▉       | 85/291 [00:02<00:08, 25.23it/s]
Loading 0:  31%|███       | 90/291 [00:02<00:06, 28.95it/s]
Loading 0:  32%|███▏      | 94/291 [00:03<00:06, 29.80it/s]
Loading 0:  34%|███▍      | 99/291 [00:03<00:05, 33.57it/s]
Loading 0:  35%|███▌      | 103/291 [00:03<00:05, 31.97it/s]
Loading 0:  37%|███▋      | 108/291 [00:03<00:05, 34.58it/s]
Loading 0:  38%|███▊      | 112/291 [00:03<00:05, 32.95it/s]
Loading 0:  40%|███▉      | 116/291 [00:03<00:05, 33.29it/s]
Loading 0:  42%|████▏     | 122/291 [00:03<00:04, 36.30it/s]
Loading 0:  44%|████▎     | 127/291 [00:03<00:04, 34.62it/s]
Loading 0:  46%|████▌     | 133/291 [00:04<00:05, 31.25it/s]
Loading 0:  47%|████▋     | 137/291 [00:04<00:04, 31.08it/s]
Loading 0:  48%|████▊     | 141/291 [00:04<00:05, 29.02it/s]
Loading 0:  51%|█████     | 147/291 [00:04<00:04, 33.56it/s]
Loading 0:  52%|█████▏    | 151/291 [00:04<00:04, 32.77it/s]
Loading 0:  54%|█████▎    | 156/291 [00:04<00:03, 35.27it/s]
Loading 0:  55%|█████▍    | 160/291 [00:05<00:03, 33.76it/s]
Loading 0:  57%|█████▋    | 165/291 [00:05<00:03, 35.44it/s]
Loading 0:  58%|█████▊    | 169/291 [00:05<00:03, 33.67it/s]
Loading 0:  60%|█████▉    | 174/291 [00:05<00:03, 35.96it/s]
Loading 0:  61%|██████    | 178/291 [00:05<00:03, 33.37it/s]
Loading 0:  63%|██████▎   | 183/291 [00:05<00:02, 36.82it/s]
Loading 0:  64%|██████▍   | 187/291 [00:05<00:03, 26.14it/s]
Loading 0:  66%|██████▌   | 191/291 [00:06<00:03, 26.40it/s]
Loading 0:  67%|██████▋   | 194/291 [00:06<00:04, 23.97it/s]
Loading 0:  69%|██████▉   | 201/291 [00:06<00:02, 31.64it/s]
Loading 0:  70%|███████   | 205/291 [00:06<00:02, 30.59it/s]
Loading 0:  72%|███████▏  | 210/291 [00:06<00:02, 33.09it/s]
Loading 0:  74%|███████▎  | 214/291 [00:06<00:02, 32.24it/s]
Loading 0:  75%|███████▌  | 219/291 [00:06<00:02, 34.81it/s]
Loading 0:  77%|███████▋  | 223/291 [00:06<00:02, 33.55it/s]
Loading 0:  78%|███████▊  | 227/291 [00:07<00:01, 33.66it/s]
Loading 0:  79%|███████▉  | 231/291 [00:07<00:01, 33.94it/s]
Loading 0:  81%|████████  | 235/291 [00:07<00:02, 25.48it/s]
Loading 0:  82%|████████▏ | 239/291 [00:07<00:02, 25.04it/s]
Loading 0:  85%|████████▍ | 246/291 [00:07<00:01, 31.70it/s]
Loading 0:  86%|████████▌ | 250/291 [00:07<00:01, 31.03it/s]
Loading 0:  88%|████████▊ | 255/291 [00:08<00:01, 33.40it/s]
Loading 0:  89%|████████▉ | 259/291 [00:08<00:01, 31.85it/s]
Loading 0:  91%|█████████ | 264/291 [00:08<00:00, 33.96it/s]
Loading 0:  92%|█████████▏| 268/291 [00:08<00:00, 32.39it/s]
Loading 0:  94%|█████████▍| 273/291 [00:08<00:00, 35.46it/s]
Loading 0:  95%|█████████▌| 277/291 [00:08<00:00, 33.16it/s]
Loading 0:  97%|█████████▋| 281/291 [00:08<00:00, 32.41it/s]
Loading 0:  98%|█████████▊| 286/291 [00:14<00:01,  2.59it/s]
Loading 0:  99%|█████████▉| 289/291 [00:14<00:00,  3.22it/s]
                                                            

Job riverise-dpo-second-v1-mkmlizer completed after 115.45s with status: succeeded
Stopping job with name riverise-dpo-second-v1-mkmlizer
Pipeline stage MKMLizer completed in 118.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service riverise-dpo-second-v1
Waiting for inference service riverise-dpo-second-v1 to be ready
Failed to get response for submission blend_remul_2024-08-22: ('http://zonemercy-lexical-nemov8-5966-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:57778->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service riverise-dpo-second-v1 ready after 191.00552487373352s
Pipeline stage MKMLDeployer completed in 191.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.403162956237793s
Received healthy response to inference request in 2.1599719524383545s
Received healthy response to inference request in 1.5408926010131836s
Received healthy response to inference request in 1.8808646202087402s
Received healthy response to inference request in 1.4362754821777344s
5 requests
0 failed requests
5th percentile: 1.4571989059448243
10th percentile: 1.4781223297119142
20th percentile: 1.5199691772460937
30th percentile: 1.608887004852295
40th percentile: 1.7448758125305175
50th percentile: 1.8808646202087402
60th percentile: 1.992507553100586
70th percentile: 2.1041504859924314
80th percentile: 2.2086101531982423
90th percentile: 2.3058865547180174
95th percentile: 2.354524755477905
99th percentile: 2.3934353160858155
mean time: 1.8842335224151612
Pipeline stage StressChecker completed in 10.39s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
starting trigger_guanaco_pipeline %s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.82s
riverise-dpo-second_v1 status is now deployed due to DeploymentManager action
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service riverise-dpo-second-v1-profiler
Waiting for inference service riverise-dpo-second-v1-profiler to be ready
Inference service riverise-dpo-second-v1-profiler ready after 190.49942421913147s
Pipeline stage MKMLProfilerDeployer completed in 190.85s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
script pods %s
Pipeline stage MKMLProfilerRunner completed in 0.36s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service riverise-dpo-second-v1-profiler is running
Tearing down inference service riverise-dpo-second-v1-profiler
Service riverise-dpo-second-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.08s
riverise-dpo-second_v1 status is now inactive due to auto deactivation removed underperforming models

Usage Metrics

Latency Metrics